bug fix and adding usage

README.md

@@ -1,34 +1,16 @@
 # deid-risk
 
-This project is intended to compute an estimated value of risk for a given database.
+The code below extends a data-frame by adding it the ability to compute de-identification risk (marketer, prosecutor).
+Because data-frames can connect to any database/file it will be the responsibility of the user to load the dataset into a data-frame.
 
-    1. Pull meta data of the database  and create a dataset via joins
+Basic examples that illustrate usage of the the framework are in the notebook folder. The example is derived from 
-    2. Generate the dataset with random selection of features
+[http://ehelthinformation.ca](http://www.ehealthinformation.ca/wp-content/uploads/2014/08/2009-De-identification-PA-whitepaper1.pdf)
-    3. Compute risk via SQL using group by
-## Python environment
 
-The following are the dependencies needed to run the code:
+Dependencies:
-
-        pandas
 	numpy 
-        pandas-gbq
+	pandas
-        google-cloud-bigquery
 	
-        
+Limitations:
-## Usage
-
-**Generate The merged dataset**
-
-    python risk.py create --i_dataset <in dataset|schema> --o_dataset <out dataset|schema> --table <name> --path <bigquery-key-file>  --key <patient-id-field-name> [--file ]
-
-
-**Compute risk (marketer, prosecutor)**
-
-    python risk.py compute --i_dataset <dataset> --table <name> --path <bigquery-key-file>  --key <patient-id-field-name> 
-## Limitations
-    - It works against bigquery for now
 
     @TODO:    
-        - Need to write a transport layer (database interface)
-        - Support for referential integrity, so one table can be selected and a dataset derived given referential integrity
         - Add support for journalist risk

notebooks/risk.ipynb

@@ -2,294 +2,121 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "metadata": {},
-   "outputs": [
+   "outputs": [],
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "dev-deid-600@aou-res-deid-vumc-test.iam.gserviceaccount.com df0ac049-d5b6-416f-ab3c-6321eda919d6 2018-09-25 08:18:34.829000+00:00 DONE\n"
-     ]
-    }
-   ],
    "source": [
+    "\"\"\"\n",
+    "    This notebook is intended to show how to use the risk framework:\n",
+    "    There are two basic usages:\n",
+    "        1. Experiment\n",
+    "            \n",
+    "            Here the framework will select a number of random fields other than the patient id and compute risk for the selection.\n",
+    "            This will repeat over a designated number of runs.\n",
+    "            \n",
+    "            The parameters to pass to enable this mode are id=<patient id>,nun_runs=<number of runs>\n",
+    "        2. Assessment\n",
+    "        \n",
+    "            Here the framework assumes you are only interested in a list of quasi identifiers and will run the evaluation once for a given list of quasi identifiers.\n",
+    "            The parameters to enable this mode are id=<patient id>,quasi_id=<list of quasi ids>\n",
+    "\"\"\"\n",
+    "import os\n",
     "import pandas as pd\n",
     "import numpy as np\n",
-    "from google.cloud import bigquery as bq\n",
     "\n",
-    "client = bq.Client.from_service_account_json('/home/steve/dev/google-cloud-sdk/accounts/vumc-test.json')\n",
+    "\n",
-    "# pd.read_gbq(query=\"select * from raw.observation limit 10\",private_key='/home/steve/dev/google-cloud-sdk/accounts/vumc-test.json')\n",
+    "#\n",
-    "jobs = client.list_jobs()\n",
+    "#-- Loading a template file\n",
-    "for job in jobs :\n",
+    "# The example taken a de-identification white-paper\n",
-    "#     print dir(job)\n",
+    "# http://www.ehealthinformation.ca/wp-content/uploads/2014/08/2009-De-identification-PA-whitepaper1.pdf\n",
-    "    print job.user_email,job.job_id,job.started, job.state\n",
+    "#\n",
-    "    break"
+    "\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from io import StringIO\n",
+    "csv = \"\"\"\n",
+    "id,sex,age,profession,drug_test\n",
+    "1,M,37,doctor,-\n",
+    "2,F,28,doctor,+\n",
+    "3,M,37,doctor,-\n",
+    "4,M,28,doctor,+\n",
+    "5,M,28,doctor,-\n",
+    "6,M,37,doctor,-\n",
+    "\"\"\"\n",
+    "f = StringIO()\n",
+    "f.write(unicode(csv))\n",
+    "f.seek(0)\n",
+    "MY_DATAFRAME = pd.read_csv(f)   "
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
-    "xo = ['person_id','date_of_birth','race']\n",
-    "xi = ['person_id','value_as_number','value_source_value']"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def get_tables(client,id,fields=[]):\n",
     "\"\"\"\n",
-    "        getting table lists from google\n",
+    "    Here's the pandas_risk code verbatim. \n",
+    "    NOTE: \n",
     "\"\"\"\n",
-    "    r = []\n",
+    "@pd.api.extensions.register_dataframe_accessor(\"deid\")\n",
-    "    ref = client.dataset(id)\n",
+    "class deid :\n",
-    "    tables = list(client.list_tables(ref))\n",
+    "    \"\"\"\n",
-    "    for table in tables :\n",
+    "        This class is a deidentification class that will compute risk (marketer, prosecutor) given a pandas dataframe\n",
-    "        ref = table.reference\n",
+    "    \"\"\"\n",
-    "        schema = client.get_table(ref).schema\n",
+    "    def __init__(self,df):\n",
-    "        names = [f.name for f in schema]\n",
+    "        self._df = df\n",
-    "        x = list(set(names) & set(fields))\n",
-    "        if x  :\n",
-    "            r.append({\"name\":table.table_id,\"fields\":names})\n",
-    "    return r\n",
     "    \n",
-    "def get_fields(**args):\n",
+    "    def risk(self,**args):\n",
     "        \"\"\"\n",
-    "        This function will generate a random set of fields from two tables. Tables are structured as follows \n",
+    "            @param  id          name of patient field            \n",
-    "        {name,fields:[],\"y\":}, with \n",
+    "            @params num_runs    number of runs (default will be 100)\n",
-    "            name     table name (needed to generate sql query)\n",
+    "            @params quasi_id \tlist of quasi identifiers to be used (this will only perform a single run)\n",
-    "            fields   list of field names, used in the projection\n",
-    "            y        name of the field to be joined.\n",
-    "        @param xo candidate table in the join\n",
-    "        @param xi candidate table in the join\n",
-    "        @param join field by which the tables can be joined.\n",
     "        \"\"\"\n",
-    "    # The set operation will remove redundancies in the field names (not sure it's a good idea)\n",
+    "        \n",
-    "#     xo = args['xo']['fields']\n",
+    "        id  = args['id']\n",
-    "#     xi = args['xi']['fields']\n",
+    "        if 'quasi_id' in args :\n",
-    "#     zi = args['xi']['name']\n",
+    "            num_runs = 1\n",
-    "#     return list(set([ \".\".join([args['xo']['name'],name]) for name in xo]) | set(['.'.join([args['xi']['name'],name]) for name in xi if name != args['join']]) )\n",
+    "            columns = list(set(args['quasi_id'])- set(id) )\n",
-    "    xo = args['xo']\n",
-    "    fields = [\".\".join([args['xo']['name'],name]) for name in args['xo']['fields']]\n",
-    "    if not isinstance(args['xi'],list) :\n",
-    "        x_ = [args['xi']]\n",
     "        else :\n",
-    "        x_ = args['xi']\n",
+    "            num_runs  = args['num_runs'] if 'num_runs' in args else 100\n",
-    "    for xi in x_ :\n",
+    "            columns = list(set(self._df.columns) - set([id]))\n",
-    "        fields += (['.'.join([xi['name'], name]) for name in xi['fields'] if name != args['join']])\n",
+    "        r   = pd.DataFrame()        \n",
-    "    return fields\n",
+    "        k = len(columns)\n",
-    "def generate_sql(**args):\n",
+    "        for i in range(0,num_runs) :\n",
-    "    \"\"\"\n",
+    "            #\n",
-    "        This function will generate the SQL query for the resulting join\n",
+    "            # let's chose a random number of columns and compute marketer and prosecutor risk\n",
-    "    \"\"\"\n",
+    "            # Once the fields are selected we run a groupby clause\n",
+    "            #\n",
+    "            if 'quasi_id' not in args :\n",
+    "                n   = np.random.randint(2,k) #-- number of random fields we are picking\n",
+    "                ii = np.random.choice(k,n,replace=False)\n",
+    "                cols = np.array(columns)[ii].tolist()\n",
+    "            else:\n",
+    "                cols \t= columns\n",
+    "                n \t= len(cols)\n",
+    "            x_ = self._df.groupby(cols).count()[id].values\n",
+    "            r = r.append(\n",
+    "                pd.DataFrame(\n",
+    "                    [\n",
+    "                        {\n",
+    "                            \"selected\":n,\n",
+    "                            \"marketer\": x_.size / np.float64(np.sum(x_)),\n",
+    "                            \"prosecutor\":1 / np.float64(np.min(x_))\n",
     "\n",
-    "    xo = args['xo']\n",
+    "                        }\n",
-    "    x_ = args['xi']\n",
+    "                    ]\n",
-    "    xo_name = \".\".join([args['prefix'],xo['name'] ]) if 'prefix' in args else xo['name']\n",
-    "    SQL = \"SELECT :fields FROM :xo.name \".replace(\":xo.name\",xo_name)\n",
-    "    if not isinstance(x_,list):\n",
-    "        x_ = [x_]\n",
-    "    f = []#[\".\".join([args['xo']['name'],args['join']] )]    \n",
-    "    INNER_JOINS = []\n",
-    "    for xi in x_ :\n",
-    "        xi_name = \".\".join([args['prefix'],xi['name'] ]) if 'prefix' in args else xi['name']\n",
-    "        JOIN_SQL = \"INNER JOIN :xi.name ON \".replace(':xi.name',xi_name)\n",
-    "        value  = \".\".join([xi['name'],args['join']])\n",
-    "        f.append(value) \n",
-    "        \n",
-    "        ON_SQL = \"\"\n",
-    "        tmp = []\n",
-    "        for term in f :\n",
-    "            ON_SQL = \":xi.name.:ofield = :xo.name.:ofield\".replace(\":xo.name\",xo['name'])\n",
-    "            ON_SQL = ON_SQL.replace(\":xi.name.:ofield\",term).replace(\":ofield\",args['join'])\n",
-    "            tmp.append(ON_SQL)\n",
-    "        INNER_JOINS += [JOIN_SQL + \" AND \".join(tmp)]\n",
-    "    return SQL + \" \".join(INNER_JOINS)\n",
-    "def get_final_sql(**args):\n",
-    "    xo = args['xo']\n",
-    "    xi = args['xi']\n",
-    "    join=args['join']\n",
-    "    prefix = args['prefix'] if 'prefix' in args else ''\n",
-    "    fields = get_fields (xo=xo,xi=xi,join=join)\n",
-    "    k = len(fields)\n",
-    "    n = np.random.randint(2,k) #-- number of fields to select\n",
-    "    i = np.random.randint(0,k,size=n)\n",
-    "    fields = [name for name in fields if fields.index(name) in i]\n",
-    "    base_sql = generate_sql(xo=xo,xi=xi,prefix)\n",
-    "    SQL = \"\"\"\n",
-    "        SELECT AVERAGE(count),size,n as selected_features,k as total_features\n",
-    "        FROM(\n",
-    "            SELECT COUNT(*) as count,count(:join) as pop,sum(:n) as N,sum(:k) as k,:fields\n",
-    "            FROM (:sql)\n",
-    "        GROUP BY :fields\n",
     "                )\n",
-    "        order by 1\n",
+    "            )\n",
+    "            g_size = x_.size\n",
+    "            n_ids = np.float64(np.sum(x_))\n",
     "\n",
-    "    \"\"\".replace(\":sql\",base_sql)\n",
+    "        return r"
-    "#     sql = \"SELECT :fields FROM :xo.name INNER JOIN :xi.name ON :xi.name.:xi.y = :xo.y \"\n",
-    "#     fields = \",\".join(get_fields(xo=xi,xi=xi,join=xi['y']))\n",
-    "    \n",
-    "    \n",
-    "#     sql = sql.replace(\":fields\",fields).replace(\":xo.name\",xo['name']).replace(\":xi.name\",xi['name'])\n",
-    "#     sql = sql.replace(\":xi.y\",xi['y']).replace(\":xo.y\",xo['y'])\n",
-    "#     return sql\n",
-    "    \n",
-    "    "
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "xo = {\"name\":\"person\",\"fields\":['person_id','date_of_birth','race','value_as_number']}\n",
-    "xi = [{\"name\":\"measurement\",\"fields\":['person_id','value_as_number','value_source_value']}] #,{\"name\":\"observation\",\"fields\":[\"person_id\",\"value_as_string\",\"observation_source_value\"]}]\n",
-    "# generate_sql(xo=xo,xi=xi,join=\"person_id\",prefix='raw')\n",
-    "fields = get_fields(xo=xo,xi=xi,join='person_id')\n",
-    "ofields = list(fields)\n",
-    "k = len(fields)\n",
-    "n = np.random.randint(2,k) #-- number of fields to select\n",
-    "i = np.random.randint(0,k,size=n)\n",
-    "fields = [name for name in fields if fields.index(name) in i]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 34,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['person.race', 'person.value_as_number', 'measurement.value_source_value']"
-      ]
-     },
-     "execution_count": 34,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "fields\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 55,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'SELECT person_id,value_as_number,measurements.value_source_value,measurements.value_as_number,value_source_value FROM person INNER JOIN measurements ON measurements.person_id = person_id '"
-      ]
-     },
-     "execution_count": 55,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "xo = {\"name\":\"person\",\"fields\":['person_id','date_of_birth','race'],\"y\":\"person_id\"}\n",
-    "xi = {\"name\":\"measurements\",\"fields\":['person_id','value_as_number','value_source_value'],\"y\":\"person_id\"}\n",
-    "generate_sql(xo=xo,xi=xi)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 59,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[('a', 'b'), ('a', 'c'), ('b', 'c')]"
-      ]
-     },
-     "execution_count": 59,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "\"\"\"\n",
-    "    We are designing a process that will take two tables that will generate \n",
-    "\"\"\"\n",
-    "import itertools\n",
-    "list(itertools.combinations(['a','b','c'],2))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "array([1, 3, 0, 0])"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "#\n",
-    "# find every table with person id at the very least or a subset of fields\n",
-    "#\n",
-    "np.random.randint(0,4,size=4)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 90,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['a']"
-      ]
-     },
-     "execution_count": 90,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "list(set(['a','b']) & set(['a']))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 120,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "x_ = 1"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "x_ = pd.DataFrame({\"group\":[1,1,1,1,1], \"size\":[2,1,1,1,1]})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
@@ -313,35 +140,125 @@
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
-       "      <th>size</th>\n",
+       "      <th>marketer</th>\n",
-       "    </tr>\n",
+       "      <th>prosecutor</th>\n",
-       "    <tr>\n",
+       "      <th>selected</th>\n",
-       "      <th>group</th>\n",
-       "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>1</th>\n",
+       "      <th>0</th>\n",
-       "      <td>1.2</td>\n",
+       "      <td>0.500000</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0.500000</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0.500000</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0.333333</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0.333333</td>\n",
+       "      <td>0.5</td>\n",
+       "      <td>2</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "text/plain": [
-       "       size\n",
+       "   marketer  prosecutor  selected\n",
-       "group      \n",
+       "0  0.500000         1.0         2\n",
-       "1       1.2"
+       "0  0.500000         1.0         3\n",
+       "0  0.500000         1.0         3\n",
+       "0  0.333333         1.0         2\n",
+       "0  0.333333         0.5         2"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "x_.groupby(['group']).mean()\n"
+    "#\n",
+    "# Lets us compute risk here for a random any random selection of quasi identifiers\n",
+    "# We will run this experiment 5 times\n",
+    "#\n",
+    "MY_DATAFRAME.deid.risk(id='id',num_runs=5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>marketer</th>\n",
+       "      <th>prosecutor</th>\n",
+       "      <th>selected</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0.5</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   marketer  prosecutor  selected\n",
+       "0       0.5         1.0         3"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#\n",
+    "# In this scenario we are just interested in sex,profession,age\n",
+    "#\n",
+    "MY_DATAFRAME.deid.risk(id='id',quasi_id=['age','sex','profession'])"
    ]
   },
   {